Tugas · MCP

Complete Task

complete_task is one of the 32 MCP tools in Weft, the AI task manager you run by talking to Claude, Cursor, Codex or ChatGPT through one MCP endpoint. The AI calls this when the work is actually finished — the card moves to Done with completion time recorded, and the optional outcome (what was done, where the result lives) is appended to the card as an "Outcome (AI, date)" note. No column id needed. Work marked as needing you does NOT move to Done: it goes to your queue with the receipt attached, and if the agent said what it would do next, accepting approves exactly that step and hands it back to the agent. If the task carries a verification plan, the server executes its checks right here — fetching the URL, looking for the quote, comparing the hash: an executable/state_delta plan whose blocking checks all pass closes verified by the server; a failed blocking check keeps the card out of Done and shows the agent what the server observed.

Weft adalah pengelola tugas AI untuk pendiri tunggal dan tim kecil.

Referensi alat dipelihara dalam bahasa Inggris: nama alat, argumen, dan contoh sama persis di setiap bahasa.

Argumen

NamaTipeWajibDeskripsi
iduuidyaTask id to complete.
outcomestringtidak1-3 sentences: what was done and where the result lives.
artifacts{ kind, uri }[]tidakEvidence a person could check without trusting the account of it — a URL, a hash, a message id.
learnings(string | { trigger, content })[]tidakUp to 3 lessons worth remembering beyond this task — they become memory notes and surface in every future get_my_work, stamped with source and date.
nextStepstringtidakWhat the agent would do next if you accept (≤200 chars) — shown above the Accept button, so accepting approves exactly that.

Hasil

The task, now in Done with completedAt set — or awaitingReview:true when it stopped at you instead.

Anotasi

Alat tulis standar. Alat ini mengubah keadaan; klien MCP bebas memanggilnya begitu tahu apa yang diinginkan pengguna. Apakah klien meminta konfirmasi adalah pilihan klien itu sendiri; spesifikasi Model Context Protocol menyarankan agar selalu ada manusia yang terlibat dan dapat menolak pemanggilan alat.

Contoh

Yang dikatakan pengguna:

"Mark the deploy task done — released in v1.2.0."

Terkait